5,442,621 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model

Research paper by Nolan Dey and collaborators. Published 2023-09-20. Topics: ALiBi position embeddings, SwiGLU nonlinearity, BTLM-3B-8K, SlimPajama dataset, parameter-efficiency.

Resource information

Authors
Nolan Dey, Daria Soboleva, Faisal Al-Khateeb, Bowen Yang, Ribhu Pathria, Hemant Khachane, Shaheer Muhammad, Zhiming, Chen, Robert Myers, Jacob Robert Steeves, Natalia Vassilieva, Marvin Tom, Joel Hestness
Research topics
ALiBi position embeddings, SwiGLU nonlinearity, BTLM-3B-8K, SlimPajama dataset, parameter-efficiency, long context performance, MPT-7B-8K, XGen-7B-8K, Hugging Face
Publication date
2023-09-20
Publication
arXiv
Last record update
Nov 3, 2026